I am trying to implement pseudo labelling for self-training.
I have a trained model which I use to run evaluations on unlabeled data. After getting the logits, i softmax them which gives me a tensor of [7x368x640].
However, when i do torch.save() to save these predictions for future training with a model with both labeled and unlabeled dataset, I realise that these files are 76M for just 1 image.
This is too large for a dataset >100k images.
Is there another way I should implement pseudolabelling?